Tethered Trust for builders MCP server
com.tetheredtrust/builderstetheredtrust.comstreamable-httpv0.65.2Scanned
Launch and keep agent tools working: MCP checks, registry publishing, x402 payment checks.
12 tools: 2 do something that can't be undone, 8 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 8
- Can send data out · 8
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Tethered Trust for builders MCP server can do
The Tethered Trust for builders MCP server is published by tetheredtrust.com, a domain the MCP Registry verified. It has 12 tools. It can do things that cannot be undone, such as sending, paying or publishing (publish_to_registry and check_payment_setup) and create or change data (8 tools: how_it_works, enrich_catalog, verify_page, verify_mcp and 4 more), but cannot delete data. 2 tools only read.
1 tool reads private data (listing_status); 8 tools bring in text other people can write (enrich_catalog, verify_page, verify_mcp and 5 more); 8 tools can send data out of your system (verify_page, verify_mcp, launch_check and 5 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 0.65.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
12 tools
Can't be undone 2Claude Code: ask
check_payment_setupCall this after building or changing a paid (x402) endpoint, or when agents' payments fail: we call it unpaid like a paying agent, read the 402, and check the payment request parse…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "check_payment_setup" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "check_payment_setup" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "check_payment_setup" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Call this after building or changing a paid (x402) endpoint, or when agents' payments fail: we call it unpaid like a paying agent, read the 402, and check the payment request parses (v1 or v2), the token's EIP-712 domain (extra.name/version) matches the contract on-chain (the usual cause of 'invalid signature' payments), network id, amount, payTo, timeout, CORS headers for browser agents, resource URL, description and Bazaar discovery. Pass / warn / fail per check with exact fixes. Never pays.
Annotations the server declares
- title: Will agents' payments go through?
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
publish_to_registryCall this to get an MCP server into the official MCP Registry (which Glama, PulseMCP and others import from) without mcp-publisher or DNS: first call with url returns a one-line fi…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "publish_to_registry" says "publish": a word for a change that another call does not undo.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "publish_to_registry" says "publish": it sends or publishes something to other people.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Call this to get an MCP server into the official MCP Registry (which Glama, PulseMCP and others import from) without mcp-publisher or DNS: first call with url returns a one-line file to host at https://<domain>/.well-known/mcp-registry-auth; once it's up, call again with publisher_id and we publish server.json under your domain's namespace, then re-publish every new version automatically for 90 days. $5, charged only when we publish. Remove the file to revoke.
Annotations the server declares
- title: Publish an MCP server to the official registry
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 8Claude Code: ask
enrich_catalogFor retailers and marketplaces (API key required): up to 50 products per call (SKU with title, URL or GTIN) in; each product's compatibility attributes out (standards it takes and …Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it For retailers and marketplaces (API key required): up to 50 products per call (SKU with title, URL or GTIN) in; each product's compatibility attributes out (standards it takes and provides, numeric limits, evidence level, freshness), ready to add to a product feed or UCP catalog so agents can match it to what shoppers own.
Annotations the server declares
- title: Enrich a product catalog
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
how_it_worksWhat Tethered Trust is, what it covers, where its data comes from, pricing and terms.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it What Tethered Trust is, what it covers, where its data comes from, pricing and terms.
Annotations the server declares
- title: How Tethered Trust works
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
launch_checkCall this after building or deploying an MCP server or paid agent API, or when its listings may be out of date: we check it works (as verify_mcp does), then look it up in the offic…Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "launch_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "call": a word for a change.
Description, as the server wrote it Call this after building or deploying an MCP server or paid agent API, or when its listings may be out of date: we check it works (as verify_mcp does), then look it up in the official MCP Registry (and whether the listed version is current), Glama, PulseMCP, the x402 Bazaar, npm and PyPI, plus its server card, llms.txt and robots.txt (Smithery, PulseMCP, mcp.so and Claude's directory are listed with links to check by hand). Returns a score, what's missing or stale, an ordered fix plan and a ready-to-publish server.json. Read-only.
Annotations the server declares
- title: Is this MCP server findable?
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
launch_planFor sellers: 30 days of official MCP Registry publishing on every new version, a daily listing watch (registry, Glama, x402 Bazaar, npm, PyPI, health) and daily payment checks of u…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it For sellers: 30 days of official MCP Registry publishing on every new version, a daily listing watch (registry, Glama, x402 Bazaar, npm, PyPI, health) and daily payment checks of up to 10 x402 endpoints, with one signed webhook. $12 per 30 days; renew with plan_id.
Annotations the server declares
- title: Keep my MCP server / paid API findable and payable
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
reliability_scoreBefore paying an unfamiliar x402 API, look up its payment-readiness score (0-100) from our daily unpaid checks of the x402 Bazaar: how many of its endpoints would accept an agent's…Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Before paying an unfamiliar x402 API, look up its payment-readiness score (0-100) from our daily unpaid checks of the x402 Bazaar: how many of its endpoints would accept an agent's payment, and the common problems. Free.
Annotations the server declares
- title: Can agents pay this API?
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verify_mcpCall this before you recommend, install or rely on an MCP server, after deploying one, or when a connector seems broken: we connect as an MCP client, list its tools, check each has…Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "verify_mcp" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "call": a word for a change.
Description, as the server wrote it Call this before you recommend, install or rely on an MCP server, after deploying one, or when a connector seems broken: we connect as an MCP client, list its tools, check each has a usable input schema and description, confirm the tools you name exist, and optionally run one sample call on a read-only tool. Pass / fail / couldn't-verify per check with a signed receipt. Never signs in or calls tools that change things.
Annotations the server declares
- title: Verify an MCP server works
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
verify_pageCall this before you tell someone a web page, site or deploy is done or working, or before relying on another agent's "it's live": we open the public page in a separate browser (de…Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "verify_page" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "call": a word for a change.
Description, as the server wrote it Call this before you tell someone a web page, site or deploy is done or working, or before relying on another agent's "it's live": we open the public page in a separate browser (desktop or mobile) and check what you list. It loads; this text is visible; this link or button leads to this address; no script errors; no broken same-site links. Pass / fail / couldn't-verify per check, with a screenshot and a signed receipt. Read-only: no logins, forms or purchases.
Annotations the server declares
- title: Verify a web page works
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
watch_listingCall this after launching an MCP server or paid agent API to keep it findable: we run launch_check today and every day for 30 days, and tell your webhook (signed) when something ch…Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "call": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Call this after launching an MCP server or paid agent API to keep it findable: we run launch_check today and every day for 30 days, and tell your webhook (signed) when something changes: the server stops answering, the registry listing falls behind a release, a directory drops it, robots.txt starts blocking. $3 per 30 days; call again with watch_id to renew. Returns today's full launch check.
Annotations the server declares
- title: Watch an MCP server's listings daily
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
launch_plan_statusWhere a Launch Plan stands: listings, registry version and each paid endpoint's payment check.No findings
Why it is in this group
- The name "launch_plan_status" says "status": a word for reading.
Description, as the server wrote it Where a Launch Plan stands: listings, registry version and each paid endpoint's payment check. Free.
Annotations the server declares
- title: Launch Plan status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
listing_statusWhere a watched MCP server stands right now: each directory's status, the latest changes, and when the watch ends.Reads private dataNo findings
Why it is in this group
- The name "listing_status" says "status": a word for reading.
What it can reach
- private-dataThe description's first sentence says "directory": it reads files.
Description, as the server wrote it Where a watched MCP server stands right now: each directory's status, the latest changes, and when the watch ends. Free.
Annotations the server declares
- title: Listing watch status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
64 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write8
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out8
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__builders__listing_status"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 17, 2026, 15:21 UTC, unchanged since Nov 10, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (2 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://tetheredtrust.com/mcp/builders: tools/list returned 12 tools to an anonymous client, including publish_to_registry (irreversible), check_payment_setup (irreversible), how_it_works (write), enrich_catalog (write), verify_page (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
- Warnverify_page
The server marks "verify_page" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "call": a word for a change.
- Warnverify_mcp
The server marks "verify_mcp" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "call": a word for a change.
- Warnlaunch_check
The server marks "launch_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "call": a word for a change.
The server marks "check_payment_setup" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "check_payment_setup" says "payment": a word that usually means money moves, which cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.65.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http builders https://tetheredtrust.com/mcp/buildersclaude mcp add --transport http builders https://tetheredtrust.com/mcp/buildersRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__builders__launch_plan_status",
"mcp__builders__listing_status"
],
"ask": [
"mcp__builders__how_it_works",
"mcp__builders__enrich_catalog",
"mcp__builders__verify_page",
"mcp__builders__verify_mcp",
"mcp__builders__launch_check",
"mcp__builders__publish_to_registry",
"mcp__builders__check_payment_setup",
"mcp__builders__watch_listing",
"mcp__builders__reliability_score",
"mcp__builders__launch_plan"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as builders. Review it before you use it.
Capability tags behind 10 rules
- mcp__builders__enrich_catalog untrusted-input
- mcp__builders__verify_page untrusted-input, outbound
- mcp__builders__verify_mcp untrusted-input, outbound
- mcp__builders__launch_check untrusted-input, outbound
- mcp__builders__publish_to_registry untrusted-input, outbound
- mcp__builders__check_payment_setup untrusted-input, outbound
- mcp__builders__watch_listing untrusted-input, outbound
- mcp__builders__reliability_score outbound
- mcp__builders__launch_plan untrusted-input, outbound
- mcp__builders__listing_status private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.tetheredtrust/builders/verify?hash=7bbe11147d184d5d343e07e4f292ccb61b0ed54b1fe0745c7a7a96b56a926ce7" | jq -e '.changed == false'Pinned hash 7bbe11147d18, from Nov 20, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.tetheredtrust/builders/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.tetheredtrust/builders)Source: MCP Registry. Synced Nov 20, 2026, 20:17 UTC.
Tethered Trust for builders MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Tethered Trust for builders MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 10 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Tethered Trust for builders MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Tethered Trust for builders MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: publish_to_registry and check_payment_setup.
What tools does the Tethered Trust for builders MCP server have?
- 12 tools: 2 irreversible, 8 write, 2 read. publish_to_registry, check_payment_setup, how_it_works, enrich_catalog, verify_page, verify_mcp, launch_check, watch_listing and 4 more.
Does the Tethered Trust for builders MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Tethered Trust for builders MCP server send data to outside services?
- 8 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): verify_page, verify_mcp, launch_check, publish_to_registry, check_payment_setup, watch_listing and 2 more.
Has the Tethered Trust for builders MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.